This workflow follows the Agent → HTTP Request recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"name": "2 - Chatbot Telegram SRI",
"nodes": [
{
"parameters": {
"promptType": "define",
"text": "={{ $json.message.text }}",
"options": {
"systemMessage": "0. REGLA DE REINICIO: Si el mensaje del usuario es exactamente \"/start\" o \"/reiniciar\", IGNORA todo el historial de conversaci\u00f3n anterior y NO uses ninguna herramienta. Responde \u00fanicamente con un saludo cordial de bienvenida como asistente de Ferreter\u00eda Proferret y pregunta en qu\u00e9 puedes ayudarle hoy.\n\nREGLAS GENERALES Y DE FORMATO:\n\n1. HERRAMIENTAS: Al usar la herramienta \"buscar_factura\", ignora cualquier contenido largo, XML, PDF o texto en base64. Extrae \u00fanicamente: nombre del cliente, RUC/c\u00e9dula, fecha, categor\u00eda y valor total. Muestra un M\u00c1XIMO de 3 facturas por respuesta.\n\n2. FORMATO DE RESPUESTA: Presenta la informaci\u00f3n limpia y legible usando este esquema exacto (NO incluyas la clave de acceso de 49 d\u00edgitos en el resumen):\n\nSe encontraron las siguientes facturas:\n\n1. \ud83d\udcc4 Factura - [nombre]\n \u2022 RUC/C\u00e9dula: [identificacion]\n \u2022 Fecha: [AAAA-MM-DD]\n \u2022 Categor\u00eda: [categoria]\n \u2022 Total: $[valor]\n\n---\n(L\u00ednea de separaci\u00f3n entre cada factura)\n\n\u00bfDesea consultar la clave de acceso o enviar alguna por correo?",
"maxIterations": 5
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 3.1,
"position": [
-64,
-272
],
"id": "b7dc45af-a009-4226-a921-fc1a78787077",
"name": "AI Agent1"
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "={{ $('Telegram Trigger').item.json.message.chat.id }}-v3",
"contextWindowLength": 2
},
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.4,
"position": [
16,
-112
],
"id": "ab932397-5c5c-41be-b77b-0b2c68bdaa0e",
"name": "Simple Memory"
},
{
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"type": "n8n-nodes-base.telegramTrigger",
"typeVersion": 1.3,
"position": [
-272,
-272
],
"id": "a6977616-f690-44c9-8d59-c006bf1aae1c",
"name": "Telegram Trigger",
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"toolDescription": "\u00dasala para consultar la lista de comprobantes autorizados y buscar facturas por el nombre del cliente, RUC, c\u00e9dula, fecha o categor\u00eda. Retorna los datos clave y la clave de acceso de los comprobantes.",
"url": "=http://localhost:4000/api/sri/comprobantes-ia",
"sendQuery": true,
"queryParameters": {
"parameters": [
{
"name": "limit",
"value": "3"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.httpRequestTool",
"typeVersion": 4.4,
"position": [
256,
-80
],
"id": "0b94cd10-c5e3-4776-8576-ea643926ff0b",
"name": "buscar_factura"
},
{
"parameters": {
"descriptionType": "manual",
"toolDescription": "\u00dasala para reenviar o enviar el correo electr\u00f3nico con los detalles o comprobante de la factura a la direcci\u00f3n indicada por el usuario. IMPORTANTE: \u00dasala SOLO UNA VEZ por solicitud. Una vez enviada, detente y confirma al usuario por Telegram.",
"fromEmail": "kam.santana@yavirac.edu.ec",
"toEmail": "={{ $fromAI(\"toEmail\", \"El correo electr\u00f3nico del cliente\") }}",
"subject": "={{ $fromAI(\"subject\", \"El asunto del correo\") }}",
"emailFormat": "text",
"text": "={{ $fromAI(\"body\", \"Escribe aqu\u00ed el resumen detallado de la factura incluyendo obligatoriamente: Nombre del cliente, RUC/C\u00e9dula, Fecha, Categor\u00eda y Valor total extra\u00eddos del historial de la conversaci\u00f3n.\") }}",
"options": {}
},
"type": "n8n-nodes-base.emailSendTool",
"typeVersion": 2.1,
"position": [
128,
-80
],
"id": "4505fb9b-7e47-4958-bccf-bcd629b1b615",
"name": "enviar_correo",
"credentials": {
"smtp": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"method": "POST",
"url": "https://api.telegram.org/bot8943655662:AAEfl1dxsEOd3e2Qs0Y4hYZrMsY7XbUr-MQ/sendMessage",
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={\n \"chat_id\": {{ $('Telegram Trigger').item.json.message.chat.id }},\n \"text\": {{ JSON.stringify($json.output) }}\n}",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.4,
"position": [
256,
-272
],
"id": "e36849d4-3443-433a-818a-cfe971c1b5fd",
"name": "HTTP Request"
},
{
"parameters": {
"model": "llama-3.3-70b-versatile",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatGroq",
"typeVersion": 1,
"position": [
-176,
-64
],
"id": "2ebbcc9f-e52f-4c3f-8734-21d328db534c",
"name": "Groq Chat Model",
"credentials": {
"groqApi": {
"name": "<your credential>"
}
}
}
],
"connections": {
"AI Agent1": {
"main": [
[
{
"node": "HTTP Request",
"type": "main",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent1",
"type": "ai_memory",
"index": 0
}
]
]
},
"Telegram Trigger": {
"main": [
[
{
"node": "AI Agent1",
"type": "main",
"index": 0
}
]
]
},
"buscar_factura": {
"ai_tool": [
[
{
"node": "AI Agent1",
"type": "ai_tool",
"index": 0
}
]
]
},
"enviar_correo": {
"ai_tool": [
[
{
"node": "AI Agent1",
"type": "ai_tool",
"index": 0
}
]
]
},
"HTTP Request": {
"main": [
[]
]
},
"Groq Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent1",
"type": "ai_languageModel",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1",
"binaryMode": "separate"
},
"versionId": "a501c9e2-0927-45b0-84ad-17cc7ac92cac",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "mtjBeU1DCnasZBUS",
"tags": []
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
groqApismtptelegramApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
2 - Chatbot Telegram SRI. Uses agent, memoryBufferWindow, telegramTrigger, httpRequestTool. Event-driven trigger; 7 nodes.
Source: https://github.com/kamsantana/PROYECTO-FACTURACION-N8N/blob/main/n8n-workflow/workflow-2-chatbot-telegram.json — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Bitlab-Chatbot. Uses telegramTrigger, telegram, snowflake, httpRequest. Event-driven trigger; 87 nodes.
god_is_typing v2.6 (Multi-channel: Telegram + Web). Uses telegramTrigger, telegram, supabase, httpRequest. Event-driven trigger; 66 nodes.
ALTUS v8 — Garage Force AI Command Center. Uses telegramTrigger, telegram, httpRequest, agent. Event-driven trigger; 42 nodes.
ALTUS v8 — Garage Force AI Command Center. Uses telegramTrigger, telegram, httpRequest, agent. Event-driven trigger; 40 nodes.
ALTUS v8 — Garage Force AI Command Center. Uses telegramTrigger, telegram, httpRequest, agent. Event-driven trigger; 39 nodes.